With the emergence of web 2.0, there is a deluge of online text. Technologies like online communities, social media, crowdfunding platforms have further contributed to the volume of content. From the firm's perspective, the importance of creating engaging content on social media platforms and as well as understanding consumer's sentiment is of supreme importance. The unstructured and noisy nature of the text and social media data often poses significant challenges for organizations in leveraging them for decision making. The workshop would try to address at a basic level how we can quantitatively analyse online text, with a special focus on social media data. This workshop aims to provide a general overview of the different quantitative methods of extracting and analysing online text. The workshop will also focus on some of the recent papers that have used text analytics for management problems.
About the Speaker
Prof. Adrija Majumdar is an Assistant Professor in the Information Systems area. She completed her PhD from Indian Institute of Management Calcutta in Management Information Systems. Her research interests include social media, information disclosures, crowdfunding, and text mining. Her research articles have been published in reputed peer-reviewed journals such as Information & Management, International Journal of Information Management, International Journal of Production Economics, Journal of Organizational Computing and Electronic Commerce, and Annals of Operations Research, etc. She has presented her work in several international and national conferences and has won two best paper awards for her dissertation work. Her research articles have appeared in conference proceedings of IEEE, ACM, and Lecture Notes in Business Information Processing, etc. Her teaching interests are in the area of Managerial computing, Transforming Business with IT, Use of social media, and Text analytics. She has earlier worked as a senior research assistant at City University of Hong Kong, Kowloon and in Cognizant Technology and Solutions.
India has embarked on one of the world's largest vaccination drives ever to control COVID-19 in the country. Considerable challenges exist in the implementation of the vaccination drive due to the large population and the need to achieve high vaccine coverage in the face of supply and vaccine administration capacity constraints. Given the considerable heterogeneity and uncertainty in the transmission of COVID-19 in urban and rural areas or across age groups, identifying and prioritising vaccination strategies based on cost-effectiveness evidence can aid in understanding how best to allocate limited supply and resources. In this work, we determine the cost-effectiveness of seroprevalence-based vaccination strategies by combining epidemiological and supply chain modeling. We use an epidemiological model of transmission dynamics of SARS-Cov-2 and to estimate the health outcomes of different seroprevalence-based vaccination strategies. We develop a supply chain model based on the resources available in the Universal Immunization Program (UIP) to support COVID-19 vaccination and determine the appropriate allocation of these resources to support the different vaccination strategies and estimate the cost of vaccine administration.
About the Speaker
Sripad Devalkar is an Associate Professor of Operations Management at the Indian School of Business (ISB). His main research interests fall under the broad themes of non-profit and public sector operations, and agricultural and food supply chains. In these thematic areas, he is interested in understanding how the interaction of operational, financial and risk management decisions affect outcomes. Prior to starting his academic career, Sripad was a consultant with a supply chain consulting firm. Sripad has a PhD from the Stephen M. Ross School of Business at the University of Michigan, MBA from IIM Ahmedabad and BTech from IIT Madras.
In this talk we will consider two simple statistical problems, estimation of the mean of a finite population, and prediction of the right kind of treatment for a particular patient given several available options. The latter is in the realm of personalized treatment. We find that the resolution of these statistical problems leads to some interesting and at the same time very surprising theoretical insights about the usefulness of small data and big data in statistics. Note, by small data we mean a small to moderate size random sample drawn from a finite population, while by big data we mean a non-random sample of very big size.
About the Speaker
Tathagata Bandyopadhyay is a professor at the Production & Quantitative Methods Area of the institute. His research is focussed on statistical inference, and developing new statistical methodologies for different areas of applications.